Abstract
Mobile devices today contain many power hungry subsystems and execute different applications. Standard power management is not aware of the desired battery lifetime and has no visibility into which applications are executing. However, power consumption is strongly dependent on which applications are executed. In this work, we propose a novel power characterization strategy for mobile devices called application-dependent power states (AP-states). Based on that, we formulate a management problem to improve performance under battery lifetime constraints, and we implement the management framework on a real Android device. We call our framework BLAST: Battery Lifetime-constrained Adaptation with Selected Target. The goal of such framework is to maximize performance while letting the device battery to last at least for a certain required lifetime, and only requires the user to select the desired target lifetime. The implementation does not require OS modifications and can be ported and installed to any Android device. We experimentally verify that our strategy can still meets user experience requirements with a selected target battery lifetime extension of at least 25%.
Highlights
Mobile devices such as smartphones and tablets contain a variety of power hungry subsystems (CPU, GPU, camera, display, antennas, etc.) and execute applications with different requirements: from browsing, to multimedia, to gaming and many more
We show that our strategy can still meets user experience requirements with a selected target battery lifetime extension of at least 25%
In this work we presented BLAST: Battery Lifetimeconstrained Adaptation with Selected Target
Summary
Mobile devices such as smartphones and tablets contain a variety of power hungry subsystems (CPU, GPU, camera, display, antennas, etc.) and execute applications with different requirements: from browsing, to multimedia, to gaming and many more. To the best of our knowledge, no work addresses the problem of maximizing performance while ensuring that a minimum battery lifetime for mobiles is met Such scenario is better explained by a motivational example in the subsection. The power management of today’s mobile devices is implemented at the OS level and regards mainly CPU and GPU. Today’s standard governor, the ondemand, scales frequency over time depending on CPU (or GPU) utilization Such approach has two main limitations: (i) it is agnostic of which application is currently running on the device and (ii) it does not account for battery lifetime. BLAST is a novel power management framework for mobile devices, which dynamically adapts to different applications while ensuring a predefined (e.g. selected) battery lifetime.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
